Skip to content

添加了基于 AirSim 仿真环境,用神经网络实现无人机的四种控制 - #154

Open
yi0330 wants to merge 18 commits into
OpenHUTB:masterfrom
yi0330:master
Open

yi0330 wants to merge 18 commits into
OpenHUTB:masterfrom
yi0330:master

Conversation

@yi0330

@yi0330 yi0330 commented Oct 5, 2026 •

Copy link
Copy Markdown

修改概述:

修改的详细描述

  1. 基于 AirSim 1.8.1 + Unreal Blocks 仿真环境,完成神经网络 "感知 — 规划 — 控制" 四任务代码:Task1 键盘遥控、Task2 深度相机神经网络避障与轨迹跟踪、Task3 LiDAR 神经网络 SLAM 建图导航、Task4 端到端 CNN(深度图→(v, ω) 行为克隆)。
  2. 所有模块均提供 main.py 入口与 launch/*.launch 启动文件,支持 Ubuntu 20.04 ROS Noetic / Humble 环境运行;配套 main.sh/main.bat 一键启动、Dockerfile、catkin 包配置(package.xml/ CMakeLists.txt)。
  3. 新增 mkdocs 文档站(Material 主题):包含环境部署、四个任务的操作步骤、计算原理公式、mermaid 算法流程图、源码解析与性能评价表,首页含跳转各任务示例的链接。

经过了什么样的测试?

  1. 操作系统:Windos10/11、Ubuntu 20.04/22.04
  2. Python 版本:3.10/3.11
  3. 基础校验:全部 Python 文件 py_compile 语法校验通过;
    AirSim 实机仿真验证:Task1 键盘控制跑通;Task2 神经网络避障与轨迹跟踪跑通;Task3 LiDAR 点云(13398 点 / 帧)配置正确、网络训练出 explorer_net.pt 并完成导航;Task4 采集 844 帧深度数据 → 训练出 e2e_cnn.pt → 端到端推理飞行跑通;
    mkdocs build 构建通过、无链接告警。

运行效果(动图、视频、图片、链接等)

task1_keyboard task2_avoid task3_slam_nav task4_e2e(1) task4_e2e(2)

修改所对应的前后效果(代码/网页):

所使用具体的大模型声明:无

@donghaiwang donghaiwang left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

没有文档,请查看其他提交

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

命名不符合要求

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

生成的网页不能添加到仓库

This branch has not been deployed

No deployments
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants